The Monthly Newsletter of IEEE Vehicular Technology Society—September 2021

header
Forward to a Colleague | RSS Join Our LinkedIn Group Join Our LinkedIn Group
spacer spacer
From the IEEE Transactions on Vehicular Technology
Research in Deep Neural Networks
Sangseok Yun, Jae-Mo Kang, Sooyong Choi, and Il-Min Kim

Full title—Cooperative Inference of DNNs Over Noisy Wireless Channels

This work studies cooperative inference of deep neural networks (DNNs), in which the inference process is performed in a cooperative manner by an edge device and an edge server. In particular, a practical noisy wireless channel between the edge device and the edge server is considered in this work, unlike the previous works which only considered ideal and simplistic error-free communications between them.

To prevent the prediction of DNNs from being inaccurate, the communication errors caused by the noisy wireless channel must be appropriately mitigated. Thus, in the proposed cooperative DNN inference, a hybrid automatic repeat request with chase combining (HARQ-CC) is adopted with a practical error correction code (ECC).

Analyzing the end-to-end latency of the proposed cooperative DNN inference, we jointly determine the optimal code rate of the ECC and the optimal location at which the DNN must be split into two parts for the edge device and the edge server to minimize the end-to-end latency.

The experimental results show that the proposed cooperative DNN inference considerably outperforms other comparable schemes in previous works.

Full Article: IEEE Transactions on Vehicular Technology, Volume 70, Number 8, August 2021

spacer
spacer
spacer spacer
Previous Article Previous Article
Next Article Next Article
Return to Top Return to Top
spacer spacer
Home Return Home
Print This Article Print This Article
spacer spacer
Share Share This Article Share Share Share
spacer
spacer
In This Issue
Message from the EiC
spacer
Society
Fellowship Nominations
spacer
Mobile Radio
Patient-Researcher Connection via 5G
spacer
Connected and Automated Vehicles
Coexistence of V2X Technologies
spacer
From the IEEE Transactions on Vehicular Technology
Research in Deep Neural Networks
spacer
From the IEEE Open Journal of Vehicular Technology
Post-COVID-19 Era ICT Framework
spacer

Editor-in-Chief

F. Richard Yu

Jump to
Conference News
Jump to
Pubs and Videos

IEEE VTS Website

News
Member Resources
Conferences
Publications
Tech Communities
About Us
spacer

CONFERENCE NEWS and LATEST UPDATES

IEEE VTC2021-Fall

27 – 30 Sep 2021

Virtual Event

Visit the IEEE VTC2021-Fall website

IEEE VPPC 2021

25 – 28 Oct 2021

Gijón, Spain

Visit the IEEE VPPC 2021 website

IEEE VTC2022-Spring

19 – 22 Jun 2022

Helsinki, Finland

Accepting papers now!

FREE for VTS Members
VTS Resource Center
VTS Resource Center
A Multimedia
Educational Library
IEEE Vehicular
Technology Magazine

Volume 16, Number 3
NEW IEEE Open Journal of
Vehicular Technology
IEEE Open Journal on Vehicular Technology
IEEE Transactions on
Vehicular Technology

Volume 70, Number 8
Browse all
Past Issues of
  50 most popular VTM articles   50 most popular TVT articles  
header
Copyright © IEEE

To ensure delivery, please add vts@ieee.org to your email address book or Safe Sender List. If you are still having problems receiving our emails, see our whitelisting page for more details.
Vehicular Technology Society Homepage IEEE Homepage